DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well...
Tested on 2 benchmarks. Top scores: Chatbot Arena Elo — Overall (1395.6%), Aider polyglot (55.1%).
Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.
Chatbot Arena overall Elo rating. Crowdsourced human preference ranking from blind head-to-head comparisons across all topics.
- Typetext
- Context164K tokens (~82 books)
- ReleasedMar 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.002
Frequently Asked Questions
Key facts · as of 2026-10-05
- DeepSeek V3 0324 by DeepSeek. Not enough public benchmark scores to rank yet.
- List price $0.25 input · $1.00 output per 1M tokens (as of 2026-10-05).
- Sold by 2 providers (as of 2026-10-05): SiliconFlow (fp8) $0.25 in / $1.00 out · GMICloud (fp8) $0.29 in / $1.14 out. Every provider
How to cite · data as of 2026-10-05
DeepSeek V3 0324 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/deepseek-chat-v3-0324
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP